h2oaiGH-16161 Fix parquet export NPE (h2oai#16175)

Author: krasinski

h2o-parsers/h2o-parquet-parser/src/main/java/water/parser/parquet/FrameParquetExporter.java

@@ -112,7 +112,11 @@ public void map(Chunk[] cs) {
                                 group = group.append(currColName, cs[j].at8(i));
                                 break;
                             case (T_STR):
-                                group = group.append(currColName, cs[j].atStr(new BufferedString(), i).toString());
+                                if (cs[j].isNA(i)) {
+                                    group = group.append(currColName, "");
+                                } else {
+                                    group = group.append(currColName, cs[j].atStr(new BufferedString(), i).toString());
+                                } 
                                 break;
                             case (T_CAT):
                                 if (cs[j].isNA(i)) {

h2o-py/tests/testdir_misc/pyunit_export_parquet_npe.py

@@ -0,0 +1,21 @@
+import sys
+import tempfile
+
+sys.path.insert(1, "../../../")
+import h2o
+from tests import pyunit_utils
+
+
+def test_export_file_npe_gh_16161():
+    with tempfile.TemporaryDirectory() as dir:
+        df = h2o.create_frame(rows=100, cols=10, string_fraction=0.1, seed=5, seed_for_column_types=25)
+        h2o.export_file(df, path=dir, format="parquet", write_checksum=False)
+
+
+if __name__ == "__main__":
+    pyunit_utils.standalone_test(test_export_file_npe_gh_16161)
+else:
+    test_export_file_npe_gh_16161()
+
+
+

h2o-r/tests/testdir_parser/runit_GH_16161_parquet_npe.R

@@ -0,0 +1,19 @@
+setwd(normalizePath(dirname(R.utils::commandArgs(asValues = TRUE)$"f")))
+source("../../scripts/h2o-r-test-setup.R")
+
+test.parseParquetString<- function() {
+  df <- h2o.createFrame(rows = 100,
+    cols = 10,
+    string_fraction = 0.1, # create one string column
+    seed = 5,
+    seed_for_column_types = 25)
+  target <- file.path(sandbox(), "createdFrame.parquet")
+  h2o.exportFile(data = df,
+    path = target,
+    format = "parquet",
+    write_checksum = FALSE)
+  df2 <- h2o.importFile(target)
+  compareFrames(df, df2)
+}
+
+doTest("Test Parquet String export error.", test.parseParquetString)